Subterranean drill bit management system

1. A method comprising:

training a first neural network of a supervised learning model to identify a location, an extent, a type, and a consistency of damage to a drill bit or bottom hole assembly based on images depicting damaged components of the drill bit or bottom hole assembly;

using the trained first neural network to identify the location, the extent, the type, and the consistency of damage to the drill bit or bottom hole assembly in at least one image obtained of the drill bit or bottom hole assembly;

based on the identified the location, the extent, the type, and the consistency of damage to the drill bit or bottom hole assembly, training a second neural network of the supervised learning model to identify a cause of damage to the drill bit or bottom hole assembly;

using the trained second neural network to identify the cause of damage to the drill bit or bottom hole assembly; and

generating a graphical output based on the identified location, extent, type and consistency of damage to the drill bit or bottom hole assembly.

2. The method of claim 1 , wherein the type indicates a fracture pattern of the damage to the drill bit or bottom hole assembly, wherein the fracture pattern comprises smooth wear, a tangential cutter fracture, spalling, heat checking, or blade wear scars.

3. The method of claim 1 , wherein the extent indicates an amount of wear on the drill bit or bottom hole assembly below threshold levels.

4. The method of claim 1 , wherein the supervised learning model comprises a scale-invariant feature transform (SIFT) technique, a histogram of gradients (HOG) technique, local binary patterns (LBP), or wavelet transforms, or any combinations thereof.

5. The method of claim 1 , wherein the supervised learning model comprises linear discriminant analysis, a support vector machine, a k-nearest neighbor technique, a random forest learning technique, or any combination thereof.

6. The method of claim 1 , further comprising generating a processed image by applying at least one modification to an image of the images depicting damaged components of the drill bit or bottom hole assembly, wherein the at least one modification comprises a rotation modification, a translation modification, a scaling modification, a red-green-blue (RGB) scale modification, or a hue-saturation-intensity (HSI) scale modification.

7. The method of claim 6 , wherein generating the processed image further comprises modifying an image of the images depicting damaged components of the drill bit or bottom hole assembly to be from a uniform perspective.

8. The method of claim 1 , wherein the trained first neural network of the supervised learning model extracts a feature from the at least one image obtained of the drill bit or bottom hole assembly.

9. The method of claim 8 , wherein the feature is extracted based on performing edge detection.

10. The method of claim 1 , comprising modifying a design of the drill bit or bottom hole assembly based on the identified cause of damage to the drill bit or bottom hole assembly.

11. The method of claim 1 , wherein the location indicates a spatial orientation and a position with respect to the drill bit or bottom hole assembly.

12. The method of claim 1 , wherein the consistency indicates whether damage is repeated in other locations on the drill bit or bottom hole assembly.

13. A system comprising:

a processor to:

train a first neural network of a supervised learning model to identify a location, an extent, a type, and a consistency of damage to the drill bit or bottom hole assembly based on images depicting damaged components of the drill bit or bottom hole assembly;

identify via the trained first neural network, the location, the extent, the type, and the consistency of damage to the drill bit or bottom hole assembly in an at least one image obtained of the drill bit or bottom hole assembly;

train a second neural network of the supervised learning model to identify a cause of damage to the drill bit or bottom hole assembly based on the identified the location, the extent, the type, and the consistency of damage to the drill bit or bottom hole assembly;

identify, via the trained second neural network, the cause of damage to the drill bit or bottom hole assembly; and

generate a graphical output based on the identified location, extent, type and consistency of damage to the drill bit or the bottom hole assembly.

14. The system of claim 13 , wherein the type indicates a fracture pattern of the damage to the drill bit or bottom hole assembly, wherein the fracture pattern comprises smooth wear, a tangential cutter fracture, spalling, heat checking, or blade wear scars.

15. The system of claim 13 , wherein the extent indicates an amount of drill bit wear or an amount of bottom hole assembly wear below threshold levels.

16. The system of claim 13 , wherein the supervised learning model comprises linear discriminant analysis, a support vector machine, a k-nearest neighbor technique, a random forest learning technique, or any combination thereof.

17. One or more non-transitory computer-readable media for characterizing damage to a bit or a bottom hole assembly comprising a plurality of instructions that, in response to execution by a processor, cause the processor to:

train a first neural network of a supervised learning model to identify a location, an extent, a type, and a consistency of damage to the drill bit or bottom hole assembly based on images depicting damaged components of the drill bit or bottom hole assembly;

identify via the trained first neural network, the location, the extent, the type, and the consistency of damage to the drill bit or bottom hole assembly in an at least one image obtained of the drill bit or bottom hole assembly;

train a second neural network of the supervised learning model to identify a cause of damage to the drill bit or bottom hole assembly based on the identified the location, the extent, the type, and the consistency of damage to the drill bit or bottom hole assembly;

identify, via the trained second neural network, the cause of damage to the drill bit or bottom hole assembly; and

generate a graphical output based on the identified location, extent, type and consistency of cause of damage to the drill bit or the bottom hole assembly.

18. The one or more non-transitory computer-readable media of claim 17 , wherein the plurality of instructions direct the processor to recommend a design of the drill bit or bottom hole assembly based on the identified cause of damage to the drill bit or bottom hole assembly.